Update app.py

app.py

@@ -24,7 +24,7 @@ def load_model(model_name, eight_bit=0, device_map="auto"):
     print('gpu_count', gpu_count)
 
     tokenizer = transformers.LlamaTokenizer.from_pretrained(model_name)
-    model = transformers.LLaMAForCausalLM.from_pretrained(
+    model = transformers.LlamaForCausalLM.from_pretrained(
         model_name,
         #device_map=device_map,
         #device_map="auto",
@@ -38,7 +38,7 @@ def load_model(model_name, eight_bit=0, device_map="auto"):
 
     generator = model.generate
 
-load_model("./pretrained")
+load_model("zl111/ChatDoctor")
 
 history = []